COVID-19(CORONA VIRUS) : EXPLORATORY DATA ANALYSIS¶
In [74]:
# Installing Dependencies
!pip install pycountry_convert
!pip install folium
!wget https://raw.githubusercontent.com/tarunk04/COVID-19-CaseStudy-and-Predictions/master/models/model_deaths.h5
!wget https://raw.githubusercontent.com/tarunk04/COVID-19-CaseStudy-and-Predictions/master/models/model_confirmed.h5
!pip install keras
!pip install tensorflow
!pip install --upgrade pip
In [75]:
#!pip install tensorflow
!conda install tensorflow --yes
In [76]:
!pip install imgkit
In [77]:
!pip install wkhtmltopdf
In [78]:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import ticker
import pycountry_convert as pc
import folium
from datetime import datetime,timedelta, date
from scipy.interpolate import make_interp_spline, BSpline
import plotly.express as px
import json, requests
from pandas.plotting import table
from keras.layers import Input, Dense, Activation, LeakyReLU
from keras import models
from keras.optimizers import RMSprop,Adam
import imgkit
%matplotlib inline
In [79]:
df_confirmed = pd.read_csv('https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_confirmed_global.csv')
df_deaths = pd.read_csv('https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_deaths_global.csv')
df_recovered = pd.read_csv('https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_recovered_global.csv')
df_covid19 = pd.read_csv("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/web-data/data/cases_country.csv")
df_table = pd.read_csv("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/web-data/data/cases_time.csv",parse_dates=['Last_Update'])
In [80]:
df_covid19.head()
Out[80]:
In [81]:
df_confirmed.head()
Out[81]:
In [82]:
df_deaths.head()
Out[82]:
In [83]:
df_recovered.head()
Out[83]:
In [84]:
df_confirmed = df_confirmed.rename(columns={'Province/State':'state','Country/Region':'country'})
df_deaths = df_deaths.rename(columns={'Province/State':'state','Country/Region':'country'})
df_recovered = df_recovered.rename(columns={'Province/State':'state','Country/Region':'country'})
df_covid19 = df_covid19.rename(columns={'Country_Region':'country'})
df_covid19['Active'] = df_covid19['Confirmed'] - df_covid19['Recovered'] - df_covid19['Deaths']
In [85]:
# Changing the conuntry names as required by pycountry_convert Lib
df_confirmed.loc[df_confirmed['country'] == "US", "country"] = "USA"
df_deaths.loc[df_deaths['country'] == "US", "country"] = "USA"
df_covid19.loc[df_covid19['country'] == "US", "country"] = "USA"
df_table.loc[df_table['Country_Region'] == "US", "Country_Region"] = "USA"
df_recovered.loc[df_recovered['country'] == "US", "country"] = "USA"
df_confirmed.loc[df_confirmed['country'] == 'Korea, South', "country"] = 'South Korea'
df_deaths.loc[df_deaths['country'] == 'Korea, South', "country"] = 'South Korea'
df_covid19.loc[df_covid19['country'] == "Korea, South", "country"] = "South Korea"
df_table.loc[df_table['Country_Region'] == "Korea, South", "Country_Region"] = "South Korea"
df_recovered.loc[df_recovered['country'] == 'Korea, South', "country"] = 'South Korea'
df_confirmed.loc[df_confirmed['country'] == 'Taiwan*', "country"] = 'Taiwan'
df_deaths.loc[df_deaths['country'] == 'Taiwan*', "country"] = 'Taiwan'
df_covid19.loc[df_covid19['country'] == "Taiwan*", "country"] = "Taiwan"
df_table.loc[df_table['Country_Region'] == "Taiwan*", "Country_Region"] = "Taiwan"
df_recovered.loc[df_recovered['country'] == 'Taiwan*', "country"] = 'Taiwan'
df_confirmed.loc[df_confirmed['country'] == 'Congo (Kinshasa)', "country"] = 'Democratic Republic of the Congo'
df_deaths.loc[df_deaths['country'] == 'Congo (Kinshasa)', "country"] = 'Democratic Republic of the Congo'
df_covid19.loc[df_covid19['country'] == "Congo (Kinshasa)", "country"] = "Democratic Republic of the Congo"
df_table.loc[df_table['Country_Region'] == "Congo (Kinshasa)", "Country_Region"] = "Democratic Republic of the Congo"
df_recovered.loc[df_recovered['country'] == 'Congo (Kinshasa)', "country"] = 'Democratic Republic of the Congo'
df_confirmed.loc[df_confirmed['country'] == "Cote d'Ivoire", "country"] = "Côte d'Ivoire"
df_deaths.loc[df_deaths['country'] == "Cote d'Ivoire", "country"] = "Côte d'Ivoire"
df_covid19.loc[df_covid19['country'] == "Cote d'Ivoire", "country"] = "Côte d'Ivoire"
df_table.loc[df_table['Country_Region'] == "Cote d'Ivoire", "Country_Region"] = "Côte d'Ivoire"
df_recovered.loc[df_recovered['country'] == "Cote d'Ivoire", "country"] = "Côte d'Ivoire"
df_confirmed.loc[df_confirmed['country'] == "Reunion", "country"] = "Réunion"
df_deaths.loc[df_deaths['country'] == "Reunion", "country"] = "Réunion"
df_covid19.loc[df_covid19['country'] == "Reunion", "country"] = "Réunion"
df_table.loc[df_table['Country_Region'] == "Reunion", "Country_Region"] = "Réunion"
df_recovered.loc[df_recovered['country'] == "Reunion", "country"] = "Réunion"
df_confirmed.loc[df_confirmed['country'] == 'Congo (Brazzaville)', "country"] = 'Republic of the Congo'
df_deaths.loc[df_deaths['country'] == 'Congo (Brazzaville)', "country"] = 'Republic of the Congo'
df_covid19.loc[df_covid19['country'] == "Congo (Brazzaville)", "country"] = "Republic of the Congo"
df_table.loc[df_table['Country_Region'] == "Congo (Brazzaville)", "Country_Region"] = "Republic of the Congo"
df_recovered.loc[df_recovered['country'] == 'Congo (Brazzaville)', "country"] = 'Republic of the Congo'
df_confirmed.loc[df_confirmed['country'] == 'Bahamas, The', "country"] = 'Bahamas'
df_deaths.loc[df_deaths['country'] == 'Bahamas, The', "country"] = 'Bahamas'
df_covid19.loc[df_covid19['country'] == "Bahamas, The", "country"] = "Bahamas"
df_table.loc[df_table['Country_Region'] == "Bahamas, The", "Country_Region"] = "Bahamas"
df_recovered.loc[df_recovered['country'] == 'Bahamas, The', "country"] = 'Bahamas'
df_confirmed.loc[df_confirmed['country'] == 'Gambia, The', "country"] = 'Gambia'
df_deaths.loc[df_deaths['country'] == 'Gambia, The', "country"] = 'Gambia'
df_covid19.loc[df_covid19['country'] == "Gambia, The", "country"] = "Gambia"
df_table.loc[df_table['Country_Region'] == "Gambia", "Country_Region"] = "Gambia"
df_recovered.loc[df_recovered['country'] == 'Gambia, The', "country"] = 'Gambia'
# getting all countries
countries = np.asarray(df_confirmed["country"])
countries1 = np.asarray(df_covid19["country"])
# Continent_code to Continent_names
continents = {
'NA': 'North America',
'SA': 'South America',
'AS': 'Asia',
'OC': 'Australia',
'AF': 'Africa',
'EU' : 'Europe',
'na' : 'Others'
}
In [86]:
df_confirmed = df_confirmed.replace(np.nan, '', regex=True)
df_confirmed = df_confirmed.drop(['state'],axis=1)
df_confirmed.head()
Out[86]:
In [87]:
df_deaths = df_deaths.replace(np.nan, '', regex=True)
df_deaths = df_deaths.drop(['state'],axis=1)
df_deaths.head()
Out[87]:
In [88]:
df_recovered = df_recovered.replace(np.nan, '', regex=True)
df_recovered = df_recovered.drop(['state'],axis=1)
df_recovered.head()
Out[88]:
In [89]:
df_table = df_table.replace(np.nan, '', regex=True)
df_table.head()
Out[89]:
In [90]:
df_countries_cases = df_covid19.copy().drop(['Lat','Long_','Last_Update'],axis=1)
In [91]:
df_countries_cases.head()
Out[91]:
In [92]:
df_countries_cases.index = df_countries_cases['country']
df_countries_cases = df_countries_cases.drop(['country'],axis=1)
df_countries_cases.head()
Out[92]:
In [93]:
df_countries_cases = df_countries_cases.groupby(['country']).sum()
In [94]:
df_countries_cases.head()
Out[94]:
In [95]:
df_countries_cases['Mortality_Rate(per100)'] = np.round(100 * df_countries_cases['Deaths']/df_countries_cases['Confirmed'],2)
In [96]:
df_countries_cases.head()
Out[96]:
In [97]:
df_countries_cases.sort_values('Confirmed',ascending=False,inplace=True)
In [98]:
df_countries_cases.head()
Out[98]:
In [99]:
df_total_world = pd.DataFrame(df_countries_cases.sum()).transpose().style.background_gradient(cmap='prism',axis=1)
df_total_world
Out[99]:
In [100]:
df_total_world.to_excel('World_Total_COVID19_data.xlsx',engine='openpyxl')
In [101]:
df_countries = df_countries_cases.style.background_gradient(cmap='Blues',subset=["Confirmed"])\
.background_gradient(cmap='Reds',subset=["Deaths"])\
.background_gradient(cmap='Greens',subset=["Recovered"])\
.background_gradient(cmap='Purples',subset=["Active"])\
.background_gradient(cmap='YlOrBr',subset=["Mortality_Rate(per100)"])
In [102]:
df_countries
Out[102]:
In [103]:
df_countries.to_excel('World_COVID19_data.xlsx',engine='openpyxl')
In [104]:
f = plt.figure(figsize=(18,9))
f.add_subplot(111)
plt.axes(axisbelow=True)
plt.barh(df_countries_cases.sort_values('Confirmed')["Confirmed"].index[-10:],df_countries_cases.sort_values('Confirmed')["Confirmed"].values[-10:],color="mediumblue")
plt.tick_params(size=5,labelsize = 13)
plt.xlabel("Confirmed Cases",fontsize=18)
plt.title("Top 10 Countries (Confirmed Cases)",fontsize=20)
plt.grid(alpha=0.3)
plt.savefig('Top 10 Countries (Confirmed Cases).png')
In [105]:
f = plt.figure(figsize=(18,9))
f.add_subplot(111)
plt.axes(axisbelow=True)
plt.barh(df_countries_cases.sort_values('Deaths')["Deaths"].index[-10:],df_countries_cases.sort_values('Deaths')["Deaths"].values[-10:],color="red")
plt.tick_params(size=5,labelsize = 13)
plt.xlabel("Deaths Cases",fontsize=18)
plt.title("Top 10 Countries (Deaths Cases)",fontsize=20)
plt.grid(alpha=0.3)
plt.savefig('Top 10 Countries (Deaths Cases).png')
In [106]:
f = plt.figure(figsize=(18,9))
f.add_subplot(111)
plt.axes(axisbelow=True)
plt.barh(df_countries_cases.sort_values('Recovered')["Recovered"].index[-10:],df_countries_cases.sort_values('Recovered')["Recovered"].values[-10:],color="lawngreen")
plt.tick_params(size=5,labelsize = 13)
plt.xlabel("Recovered Cases",fontsize=18)
plt.title("Top 10 Countries (Recovered Cases)",fontsize=20)
plt.grid(alpha=0.3)
plt.savefig('Top 10 Countries (Recovered Cases).png')
In [107]:
df_countries_cases.corr().style.background_gradient(cmap='OrRd')
Out[107]:
In [108]:
world_map = folium.Map(location=[10,0], tiles="cartodbpositron", zoom_start=2,max_zoom=6,min_zoom=2)
for i in range(0,len(df_confirmed)):
folium.Circle(
location=[df_confirmed.iloc[i]['Lat'], df_confirmed.iloc[i]['Long']],
tooltip = "<h5 style='text-align:center;font-weight: bold'>"+df_confirmed.iloc[i]['country']+"</h5>"+
"<div style='text-align:center;'>"+"</div>"+
"<hr style='margin:10px;'>"+
"<ul style='color: #444;list-style-type:circle;align-item:left;padding-left:20px;padding-right:20px'>"+
"<li>Confirmed: "+str(df_confirmed.iloc[i,-1])+"</li>"+
"<li>Deaths: "+str(df_deaths.iloc[i,-1])+"</li>"+
"<li>Mortality Rate: "+str(np.round(df_deaths.iloc[i,-1]/(df_confirmed.iloc[i,-1]+1.00001)*100,2))+"</li>"+
"</ul>"
,
radius=(int((np.log(df_confirmed.iloc[i,-1]+1.00001)))+0.2)*50000,
color='#ff6600',
fill_color='#ff8533',
fill=True).add_to(world_map)
world_map
Out[108]:
In [109]:
df_countries = df_confirmed.groupby(['country']).sum()
In [110]:
df_countries = df_countries.sort_values(df_countries.columns[-1],ascending=False)
In [111]:
countries = df_countries[df_countries[df_countries.columns[-1]] >= 20000].index
In [112]:
countries
Out[112]:
In [113]:
def plot_params(ax,axis_label= None, plt_title = None,label_size=15, axis_fsize = 15, title_fsize = 20, scale = 'linear' ):
# Tick-Parameters
ax.xaxis.set_minor_locator(ticker.AutoMinorLocator())
ax.yaxis.set_minor_locator(ticker.AutoMinorLocator())
ax.tick_params(which='both', width=1,labelsize=label_size)
ax.tick_params(which='major', length=6)
ax.tick_params(which='minor', length=3, color='0.8')
# Grid
plt.grid(lw = 1, ls = '-', c = "0.7", which = 'major')
plt.grid(lw = 1, ls = '-', c = "0.9", which = 'minor')
# Plot Title
plt.title( plt_title,{'fontsize':title_fsize})
# Yaxis sacle
plt.yscale(scale)
plt.minorticks_on()
# Plot Axes Labels
xl = plt.xlabel(axis_label[0],fontsize = axis_fsize)
yl = plt.ylabel(axis_label[1],fontsize = axis_fsize)
def visualize_covid_cases(confirmed, deaths, continent=None , country = None , state = None, period = None, figure = None, scale = "linear"):
x = 0
if figure == None:
f = plt.figure(figsize=(10,10))
# Sub plot
ax = f.add_subplot(111)
else :
f = figure[0]
# Sub plot
ax = f.add_subplot(figure[1],figure[2],figure[3])
plt.tight_layout(pad=10, w_pad=5, h_pad=5)
stats = [confirmed, deaths]
label = ["Confirmed", "Deaths"]
if continent != None:
params = ["continent",continent]
elif country != None:
params = ["country",country]
else:
params = ["All", "All"]
color = ["darkcyan","crimson"]
marker_style = dict(linewidth=3, linestyle='-', marker='o',markersize=4, markerfacecolor='#ffffff')
for i,stat in enumerate(stats):
if params[1] == "All" :
cases = np.sum(np.asarray(stat.iloc[:,5:]),axis = 0)[x:]
else :
cases = np.sum(np.asarray(stat[stat[params[0]] == params[1]].iloc[:,5:]),axis = 0)[x:]
date = np.arange(1,cases.shape[0]+1)[x:]
plt.plot(date,cases,label = label[i]+" (Total : "+str(cases[-1])+")",color=color[i],**marker_style)
if params[1] == "All" :
Total_confirmed = np.sum(np.asarray(stats[0].iloc[:,5:]),axis = 0)[x:]
Total_deaths = np.sum(np.asarray(stats[1].iloc[:,5:]),axis = 0)[x:]
else :
Total_confirmed = np.sum(np.asarray(stats[0][stat[params[0]] == params[1]].iloc[:,5:]),axis = 0)[x:]
Total_deaths = np.sum(np.asarray(stats[1][stat[params[0]] == params[1]].iloc[:,5:]),axis = 0)[x:]
text = "From "+stats[0].columns[5]+" to "+stats[0].columns[-1]+"\n"
text += "Mortality rate : "+ str(int(Total_deaths[-1]/(Total_confirmed[-1])*10000)/100)+"\n"
text += "Last 5 Days:\n"
text += "Confirmed : " + str(Total_confirmed[-1] - Total_confirmed[-6])+"\n"
text += "Deaths : " + str(Total_deaths[-1] - Total_deaths[-6])+"\n"
text += "Last 24 Hours:\n"
text += "Confirmed : " + str(Total_confirmed[-1] - Total_confirmed[-2])+"\n"
text += "Deaths : " + str(Total_deaths[-1] - Total_deaths[-2])+"\n"
plt.text(0.02, 0.78, text, fontsize=15, horizontalalignment='left', verticalalignment='top', transform=ax.transAxes,bbox=dict(facecolor='white', alpha=0.4))
# Plot Axes Labels
axis_label = ["Days ("+df_confirmed.columns[5]+" - "+df_confirmed.columns[-1]+")","No of Cases"]
# Plot Parameters
plot_params(ax,axis_label,scale = scale)
# Plot Title
if params[1] == "All" :
plt.title("COVID-19 Cases World",{'fontsize':25})
else:
plt.title("COVID-19 Cases for "+params[1] ,{'fontsize':25})
# Legend Location
l = plt.legend(loc= "best",fontsize = 15)
if figure == None:
plt.show()
def get_total_cases(cases, country = "All"):
if(country == "All") :
return np.sum(np.asarray(cases.iloc[:,5:]),axis = 0)[-1]
else :
return np.sum(np.asarray(cases[cases["country"] == country].iloc[:,5:]),axis = 0)[-1]
def get_mortality_rate(confirmed,deaths, continent = None, country = None):
if continent != None:
params = ["continent",continent]
elif country != None:
params = ["country",country]
else :
params = ["All", "All"]
if params[1] == "All" :
Total_confirmed = np.sum(np.asarray(confirmed.iloc[:,5:]),axis = 0)
Total_deaths = np.sum(np.asarray(deaths.iloc[:,5:]),axis = 0)
mortality_rate = np.round((Total_deaths/Total_confirmed)*100,2)
else :
Total_confirmed = np.sum(np.asarray(confirmed[confirmed[params[0]] == params[1]].iloc[:,5:]),axis = 0)
Total_deaths = np.sum(np.asarray(deaths[deaths[params[0]] == params[1]].iloc[:,5:]),axis = 0)
mortality_rate = np.round((Total_deaths/Total_confirmed)*100,2)
return np.nan_to_num(mortality_rate)
def dd(date1,date2):
return (datetime.strptime(date1,'%m/%d/%y') - datetime.strptime(date2,'%m/%d/%y')).days
In [114]:
cols = 1
rows = 1
f = plt.figure(figsize=(10,10*rows))
visualize_covid_cases(df_confirmed, df_deaths,country = "All",figure = [f,rows,cols, 1])
plt.savefig('COIVD-19-World.png')
plt.show()
In [115]:
df_countries = df_countries.groupby(['country']).sum()
df_countries = df_countries.sort_values(df_countries.columns[-1],ascending=False)
countries = df_countries[df_countries[df_countries.columns[-1]]>=20000].index
cols = 2
rows = int(np.ceil(countries.shape[0]/cols))
f = plt.figure(figsize=(20,8*rows))
for i,country in enumerate(countries):
visualize_covid_cases(df_confirmed,df_deaths,country=country,figure=[f,rows,cols,i+1])
plt.savefig("Top 10 countries latest trends.png")
plt.show()
In [116]:
case_nums_country = df_confirmed.groupby("country").sum().drop(['Lat','Long'],axis =1).apply(lambda x: x[x > 0].count(), axis =0)
d = [datetime.strptime(date,'%m/%d/%y').strftime("%d %b") for date in case_nums_country.index]
f = plt.figure(figsize=(15,8))
f.add_subplot(111)
marker_style = dict(c="crimson",linewidth=6, linestyle='-', marker='o',markersize=8, markerfacecolor='#ffffff')
plt.plot(d, case_nums_country,**marker_style)
plt.tick_params(labelsize = 14)
plt.xticks(list(np.arange(0,len(d),int(len(d)/5))),d[:-1:int(len(d)/5)]+[d[-1]])
#labels
plt.xlabel("Dates",fontsize=18)
plt.ylabel("Number of Countries/Regions",fontsize=18)
plt.grid(alpha = 0.3)
plt.savefig('spread.png')
plt.show()
plt.close()
In [117]:
model = models.load_model('model_confirmed.h5')
In [118]:
model.summary()
In [119]:
data_y = np.log10(np.asarray(df_confirmed.sum()[5:]).astype("float32"))
data_x = np.arange(1,len(data_y)+1)
In [120]:
lakh = 100000
prediction_days = 10
data = np.power(10,model.predict(np.arange(1,len(data_y)+prediction_days+1)))
temp_data = df_confirmed.iloc[:,5:].sum(axis =0)
f = plt.figure(figsize=(15,10))
ax = f.add_subplot(111)
date = np.arange(0,len(temp_data))
marker_style = dict(linewidth=3, linestyle='-', marker='o',markersize=7, markerfacecolor='#ffffff')
plt.plot(date,temp_data/lakh,"-.",color="darkcyan",**marker_style, label="Actual Curve")
date = np.arange(0,len(data))
plt.plot(date,data/lakh,"-.",color="orangered",label="Predicted Curve")
nextdays = [(datetime.strptime(d[-1],'%d %b')+timedelta(days=i)).strftime("%d %b") for i in range(1,prediction_days+1)]
total = d + nextdays
text = "Prediction for next "+str(prediction_days) +" days:\n"
for i in range(prediction_days):
text += nextdays[i]+" : "+str(np.round(data[-1*(prediction_days-i)],-3)[0]/lakh)+" L\n"
plt.text(0.02, 0.78, text, fontsize=17, horizontalalignment='left', verticalalignment='top', transform=ax.transAxes,bbox=dict(facecolor='white', alpha=0.4))
# X-axis
plt.xticks(list(np.arange(0,len(total),int(len(total)/5))),d[:-1:int(len(total)/5)]+[total[-1]])
# Tick-Parameters
ax.xaxis.set_minor_locator(ticker.AutoMinorLocator())
ax.yaxis.set_minor_locator(ticker.AutoMinorLocator())
ax.tick_params(which='both', width=1,labelsize=14)
ax.tick_params(which='major', length=6)
ax.tick_params(which='minor', length=3, color='0.8')
# Grid
plt.grid(lw = 1, ls = '-', c = "0.7", which = 'major')
plt.grid(lw = 1, ls = '-', c = "0.9", which = 'minor')
# Plot Title
plt.title("COVID-19 Next 10 day Prediction Curve-Global Confirmed Cases",{'fontsize':22})
# Axis Lable
plt.xlabel("Date",fontsize =18)
plt.ylabel("Number of Confirmed Cases (Lakh)",fontsize =18)
plt.yscale("log")
plt.legend(fontsize =18)
plt.tick_params(labelsize = 13)
plt.savefig("Prediction Curve-Confirmed.png")
plt.show()
In [121]:
# Data
temp_data = np.nan_to_num(df_confirmed.sum()[5:].diff())
# Plot
f = plt.figure(figsize=(15,10))
ax = f.add_subplot(111)
date = np.arange(0,len(temp_data))
marker_style = dict(linewidth=2, linestyle='-', marker='o',markersize=5)
plt.plot(date,temp_data/1000,"-.",color="red",**marker_style)
nextdays = [(datetime.strptime(d[-1],'%d %b')+timedelta(days=i)).strftime("%d %b") for i in range(1,prediction_days+1)]
total =d+nextdays
# X-axis
plt.xticks(list(np.arange(0,len(total),int(len(total)/5))),total[:-1:int(len(total)/5)]+[total[-1]])
# Tick-Parameters
ax.xaxis.set_minor_locator(ticker.AutoMinorLocator())
ax.yaxis.set_minor_locator(ticker.AutoMinorLocator())
ax.tick_params(which='both', width=1,labelsize=12)
ax.tick_params(which='major', length=6)
ax.tick_params(which='minor', length=3, color='0.8')
# Grid
plt.grid(lw = 1, ls = '-', c = "0.85", which = 'major')
plt.grid(lw = 1, ls = '-', c = "0.95", which = 'minor')
# Plot Title
plt.title("COVID-19 Global Daily New Confirmed Cases",{'fontsize':22})
# Axis Lable
plt.xlabel("Date",fontsize =18)
plt.ylabel("Number of Daily Confirmed Cases (Thousand)",fontsize =18)
# plt.yscale("log")
plt.tick_params(labelsize = 13)
plt.savefig("daily confirmed cases global.png")
plt.show()
In [122]:
# Data
temp_data = np.nan_to_num(df_deaths.sum()[5:].diff())
# Plot
f = plt.figure(figsize=(15,10))
ax = f.add_subplot(111)
date = np.arange(0,len(temp_data))
marker_style = dict(linewidth=2, linestyle='-', marker='o',markersize=5)
plt.plot(date,temp_data/1000,"-.",color="red",**marker_style)
nextdays = [(datetime.strptime(d[-1],'%d %b')+timedelta(days=i)).strftime("%d %b") for i in range(1,prediction_days+1)]
total =d+nextdays
# X-axis
plt.xticks(list(np.arange(0,len(total),int(len(total)/5))),total[:-1:int(len(total)/5)]+[total[-1]])
# Tick-Parameters
ax.xaxis.set_minor_locator(ticker.AutoMinorLocator())
ax.yaxis.set_minor_locator(ticker.AutoMinorLocator())
ax.tick_params(which='both', width=1,labelsize=14)
ax.tick_params(which='major', length=6)
ax.tick_params(which='minor', length=3, color='0.8')
# Grid
plt.grid(lw = 1, ls = '-', c = "0.85", which = 'major')
plt.grid(lw = 1, ls = '-', c = "0.95", which = 'minor')
# Plot Title
plt.title("COVID-19 Global Daily Deaths Reported",{'fontsize':22})
# Axis Lable
plt.xlabel("Date",fontsize =18)
plt.ylabel("Number of Daily Deaths Reported (Thousand)",fontsize =18)
# plt.yscale("log")
plt.savefig("daily deaths cases Global.png")
plt.show()
In [123]:
thoudand = 1000
temp = df_confirmed.groupby('country').sum().diff(axis=1).sort_values(df_deaths.columns[-1],ascending =False).head(10).replace(np.nan,0)
threshold = 0
f = plt.figure(figsize=(20,12))
ax = f.add_subplot(111)
for i,country in enumerate(temp.index):
t = temp.loc[temp.index== country].values[0]
t = t[t>=threshold]
date = np.arange(0,len(t[:]))
plt.plot(date,t/thoudand,'-o',label = country,linewidth =2, markevery=[-1])
nextdays = [(datetime.strptime(d[-1],'%d %b')+timedelta(days=i)).strftime("%d %b") for i in range(1,prediction_days+1)]
total =d+nextdays
# X-axis
plt.xticks(list(np.arange(0,len(total),int(len(total)/5))),total[:-1:int(len(total)/5)]+[total[-1]])
# Tick-Parameters
ax.xaxis.set_minor_locator(ticker.AutoMinorLocator())
ax.yaxis.set_minor_locator(ticker.AutoMinorLocator())
ax.tick_params(which='both', width=1,labelsize=14)
ax.tick_params(which='major', length=6)
ax.tick_params(which='minor', length=3, color='0.8')
# Grid
plt.grid(lw = 1, ls = '-', c = "0.85", which = 'major')
plt.grid(lw = 1, ls = '-', c = "0.95", which = 'minor')
# Plot Title
plt.title("COVID-19 Daily Confirmed Cases in Different Countries",{'fontsize':24})
# Axis Lable
plt.xlabel("Date",fontsize =18)
plt.ylabel("Number of Daily Confirmed Cases (Thousand)",fontsize =18)
# plt.yscale("log")
plt.legend(fontsize=18)
plt.savefig("daily confirmed cases countrywise.png")
plt.show()
In [124]:
thoudand = 1000
temp = df_deaths.groupby('country').sum().diff(axis=1).sort_values(df_deaths.columns[-1],ascending =False).head(10).replace(np.nan,0)
threshold = 0
f = plt.figure(figsize=(20,12))
ax = f.add_subplot(111)
for i,country in enumerate(temp.index):
t = temp.loc[temp.index== country].values[0]
t = t[t>=threshold]
date = np.arange(0,len(t[:]))
plt.plot(date,t/thoudand,'-o',label = country,linewidth =2, markevery=[-1])
nextdays = [(datetime.strptime(d[-1],'%d %b')+timedelta(days=i)).strftime("%d %b") for i in range(1,prediction_days+1)]
total =d+nextdays
# X-axis
plt.xticks(list(np.arange(0,len(total),int(len(total)/5))),total[:-1:int(len(total)/5)]+[total[-1]])
# Tick-Parameters
ax.xaxis.set_minor_locator(ticker.AutoMinorLocator())
ax.yaxis.set_minor_locator(ticker.AutoMinorLocator())
ax.tick_params(which='both', width=1,labelsize=15)
ax.tick_params(which='major', length=6)
ax.tick_params(which='minor', length=3, color='0.8')
# Grid
plt.grid(lw = 1, ls = '-', c = "0.85", which = 'major')
plt.grid(lw = 1, ls = '-', c = "0.95", which = 'minor')
# Plot Title
plt.title("COVID-19 Daily Deaths Reported in Different Countries",{'fontsize':24})
# Axis Lable
plt.xlabel("Date",fontsize =18)
plt.ylabel("Number of Daily Deaths Reported (Thousand)",fontsize =18)
# plt.yscale("log")
plt.legend(fontsize=18)
plt.savefig("daily deaths reported countrywise.png")
plt.show()
COVID19 - INDIA DATA ANALYSIS¶
In [125]:
india_data_json = requests.get('https://api.rootnet.in/covid19-in/unofficial/covid19india.org/statewise').json()
In [126]:
df_india = pd.io.json.json_normalize(india_data_json['data']['statewise'])
df_india = df_india.set_index("state")
In [127]:
df_india = df_india.sort_values('confirmed',ascending=False)
df_india = df_india[['confirmed','active','recovered','deaths']]
df_india
Out[127]:
In [128]:
total = df_india.sum()
total.name = "Total"
df_india_total = pd.DataFrame(total).transpose().style.background_gradient(cmap='prism',axis=1)
df_india_total
Out[128]:
In [129]:
df_india_total.to_excel('India_COVID19_totalData.xlsx',engine='openpyxl')
In [130]:
df_india['Mortality_Rate(per100)'] = np.round(100 * df_india['deaths']/df_india['confirmed'],2)
df_india.sort_values('confirmed',ascending=False,inplace=True)
df_india
Out[130]:
In [131]:
df_india_styled = df_india.style.background_gradient('prism')
df_india_styled
df_india_styled = df_india.style.background_gradient(cmap='Blues',subset=["confirmed"])\
.background_gradient(cmap='Reds',subset=["deaths"])\
.background_gradient(cmap='Greens',subset=["recovered"])\
.background_gradient(cmap='Purples',subset=["active"])\
.background_gradient(cmap='YlOrBr',subset=["Mortality_Rate(per100)"])
In [132]:
df_india_styled
Out[132]:
In [133]:
df_india_styled.to_excel('India_COVID19_data.xlsx',engine='openpyxl')
In [134]:
# Adding Location data (Latitude,Longitude)
locations = {
"Kerala" : [10.8505,76.2711],
"Maharashtra" : [19.7515,75.7139],
"Karnataka": [15.3173,75.7139],
"Telangana": [18.1124,79.0193],
"Uttar Pradesh": [26.8467,80.9462],
"Rajasthan": [27.0238,74.2179],
"Gujarat":[22.2587,71.1924],
"Delhi" : [28.7041,77.1025],
"Punjab":[31.1471,75.3412],
"Tamil Nadu": [11.1271,78.6569],
"Haryana": [29.0588,76.0856],
"Madhya Pradesh":[22.9734,78.6569],
"Jammu and Kashmir":[33.7782,76.5762],
"Ladakh": [34.1526,77.5770],
"Andhra Pradesh":[15.9129,79.7400],
"West Bengal": [22.9868,87.8550],
"Bihar": [25.0961,85.3131],
"Chhattisgarh":[21.2787,81.8661],
"Chandigarh":[30.7333,76.7794],
"Uttarakhand":[30.0668,79.0193],
"Himachal Pradesh":[31.1048,77.1734],
"Goa": [15.2993,74.1240],
"Odisha":[20.9517,85.0985],
"Andaman and Nicobar Islands": [11.7401,92.6586],
"Puducherry":[11.9416,79.8083],
"Manipur":[24.6637,93.9063],
"Mizoram":[23.1645,92.9376],
"Assam":[26.2006,92.9376],
"Meghalaya":[25.4670,91.3662],
"Tripura":[23.9408,91.9882],
"Arunachal Pradesh":[28.2180,94.7278],
"Jharkhand" : [23.6102,85.2799],
"Nagaland": [26.1584,94.5624],
"Sikkim": [27.5330,88.5122],
"Dadra and Nagar Haveli":[20.1809,73.0169],
"Lakshadweep":[10.5667,72.6417],
"Daman and Diu":[20.4283,72.8397]
}
df_india["Lat"] = ""
df_india["Long"] = ""
for index in df_india.index :
df_india.loc[df_india.index == index,"Lat"] = locations[index][0]
df_india.loc[df_india.index == index,"Long"] = locations[index][1]
In [135]:
url = "https://raw.githubusercontent.com/Subhash9325/GeoJson-Data-of-Indian-States/master/Indian_States"
state_json = requests.get(url).json()
india = folium.Map(location=[23,80], zoom_start=4,max_zoom=6,min_zoom=4,height=500,width="80%")
for i in range(0,len(df_india[df_india['confirmed']>0].index)):
folium.Circle(
location=[df_india.iloc[i]['Lat'], df_india.iloc[i]['Long']],
tooltip = "<h5 style='text-align:center;font-weight: bold'>"+df_india.iloc[i].name+"</h5>"+
"<hr style='margin:10px;'>"+
"<ul style='color: #444;list-style-type:circle;align-item:left;padding-left:20px;padding-right:20px'>"+
"<li>Confirmed: "+str(df_india.iloc[i]['confirmed'])+"</li>"+
"<li>Active: "+str(df_india.iloc[i]['active'])+"</li>"+
"<li>Recovered: "+str(df_india.iloc[i]['recovered'])+"</li>"+
"<li>Deaths: "+str(df_india.iloc[i]['deaths'])+"</li>"+
"<li>Mortality Rate: "+str(np.round(df_india.iloc[i]['deaths']/(df_india.iloc[i]['confirmed']+1)*100,2))+"</li>"+
"</ul>"
,
radius=(int(np.log2(df_india.iloc[i]['confirmed']+1)))*15000,
color='#ff6600',
fill_color='#ff8533',
fill=True).add_to(india)
india
Out[135]:
In [136]:
f = plt.figure(figsize=(18,9))
f.add_subplot(111)
plt.axes(axisbelow=True)
plt.barh(df_india.sort_values('confirmed')["confirmed"].index[:],df_india.sort_values('confirmed')["confirmed"].values[:],color="mediumblue")
plt.tick_params(size=5,labelsize = 13)
plt.xlabel("Confirmed Cases",fontsize=18)
plt.title("India States (Confirmed Cases)",fontsize=20)
plt.grid(alpha=0.3)
plt.savefig('India States (Confirmed Cases).png')
In [137]:
f = plt.figure(figsize=(18,9))
f.add_subplot(111)
plt.axes(axisbelow=True)
plt.barh(df_india.sort_values('active')["active"].index[:],df_india.sort_values('active')["active"].values[:],color="yellow")
plt.tick_params(size=5,labelsize = 13)
plt.xlabel("Active Cases",fontsize=18)
plt.title("India States (ActiveCases)",fontsize=20)
plt.grid(alpha=0.3)
plt.savefig('India States (Active Cases).png')
In [138]:
f = plt.figure(figsize=(18,9))
f.add_subplot(111)
plt.axes(axisbelow=True)
plt.barh(df_india.sort_values('recovered')["recovered"].index[:],df_india.sort_values('recovered')["recovered"].values[:],color="lawngreen")
plt.tick_params(size=5,labelsize = 13)
plt.xlabel("Recovered Cases",fontsize=18)
plt.title("India States (Recovered Cases)",fontsize=20)
plt.grid(alpha=0.3)
plt.savefig('India States (Recovered Cases).png')
In [139]:
f = plt.figure(figsize=(18,9))
f.add_subplot(111)
plt.axes(axisbelow=True)
plt.barh(df_india.sort_values('deaths')["deaths"].index[:],df_india.sort_values('deaths')["deaths"].values[:],color="red")
plt.tick_params(size=5,labelsize = 13)
plt.xlabel("Deaths",fontsize=18)
plt.title("India States (Deaths)",fontsize=20)
plt.grid(alpha=0.3)
plt.savefig('India States (Deaths).png')
COVID-19 : USA TRENDS AND ANALYSIS¶
In [140]:
date_usa = datetime.strptime(df_confirmed.columns[-1],'%m/%d/%y').strftime('%m-%d-%Y')
df_temp = pd.read_csv("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_daily_reports/"+date_usa+".csv")
df_usa = df_temp.loc[df_temp['Country_Region'] == 'US']
df_usa = df_usa.rename(columns={'Admin2':'County'})
df_usa = df_usa.rename(columns={'Province_State':'State'})
df_usa
Out[140]:
In [141]:
total = df_usa.sum()
total.name = "Total"
pd.DataFrame(total).transpose().loc[:,['Confirmed','Deaths']].style.background_gradient(cmap='prism',axis=1)
Out[141]:
In [142]:
df_usa_styled = df_usa.loc[:,['Confirmed','Deaths','State']].groupby(['State']).sum().sort_values('Confirmed',ascending=False).style.background_gradient(cmap='Blues',subset=['Confirmed']).background_gradient(cmap='Reds',subset=['Deaths'])
df_usa_styled.to_excel('USA_COVID19_DATA.xlsx',engine='openpyxl')
df_usa_styled
Out[142]:
In [ ]:
In [144]:
f = plt.figure(figsize=(10,5))
f.add_subplot(111)
plt.axes(axisbelow=True)
plt.barh(df_usa.groupby(["State"]).sum().sort_values('Confirmed')["Confirmed"].index[-10:],df_usa.groupby(["State"]).sum().sort_values('Confirmed')["Confirmed"].values[-10:],color="darkcyan")
plt.tick_params(size=5,labelsize = 13)
plt.xlabel("Confirmed Cases",fontsize=18)
plt.title("Top 10 States: USA (Confirmed Cases)",fontsize=20)
plt.grid(alpha=0.3)
plt.savefig('Top 10 States_USA (Confirmed Cases).png')
In [145]:
f = plt.figure(figsize=(10,5))
f.add_subplot(111)
plt.axes(axisbelow=True)
plt.barh(df_usa.groupby(["State"]).sum().sort_values('Deaths')["Deaths"].index[-10:],df_usa.groupby(["State"]).sum().sort_values('Deaths')["Deaths"].values[-10:],color="crimson")
plt.tick_params(size=5,labelsize = 13)
plt.xlabel("Deaths",fontsize=18)
plt.title("Top 10 States: USA (Deaths Cases)",fontsize=20)
plt.grid(alpha=0.3)
plt.savefig('Top 10 States_USA (Deaths Cases).png')
In [146]:
# url = "https://raw.githubusercontent.com/Subhash9325/GeoJson-Data-of-Indian-States/master/Indian_States"
# state_json = requests.get(url).json()
df_usa = df_usa.replace(np.nan, 0, regex=True)
usa = folium.Map(location=[37, -102], zoom_start=4,max_zoom=8,min_zoom=4)
for i in np.int32(np.asarray(df_usa[df_usa['Confirmed'] > 0].index)):
folium.Circle(
location=[df_usa.loc[i]['Lat'], df_usa.loc[i]['Long_']],
tooltip = "<h5 style='text-align:center;font-weight: bold'>"+df_usa.loc[i]['State']+"</h5>"+
"<div style='text-align:center;'>"+str(np.nan_to_num(df_usa.loc[i]['County']))+"</div>"+
"<hr style='margin:10px;'>"+
"<ul style='color: #444;list-style-type:circle;align-item:left;padding-left:20px;padding-right:20px'>"+
"<li>Confirmed: "+str(df_usa.loc[i]['Confirmed'])+"</li>"+
"<li>Active: "+str(df_usa.loc[i]['Active'])+"</li>"+
"<li>Recovered: "+str(df_usa.loc[i]['Recovered'])+"</li>"+
"<li>Deaths: "+str(df_usa.loc[i]['Deaths'])+"</li>"+
"<li>Mortality Rate: "+str(np.round(df_usa.loc[i]['Deaths']/(df_usa.loc[i]['Confirmed']+1)*100,2))+"</li>"+
"</ul>"
,
radius=int((np.log2(df_usa.loc[i]['Confirmed']+1))*6000),
color='#ff6600',
fill_color='#ff8533',
fill=True).add_to(usa)
usa
Out[146]:
In [147]:
!tar cvfz allfiles.tar.gz *
In [ ]: